Update app.py
Browse files
app.py
CHANGED
@@ -24,7 +24,7 @@ def link_find(url):
|
|
24 |
|
25 |
else:
|
26 |
pass
|
27 |
-
return
|
28 |
#https://huggingface.co/spaces/Omnibus/crawl
|
29 |
|
30 |
def sitemap(url,level):
|
@@ -32,7 +32,7 @@ def sitemap(url,level):
|
|
32 |
if url != "" and url != None:
|
33 |
link1=link_find(url)
|
34 |
if level >=2:
|
35 |
-
for i,ea in enumerate(link1):
|
36 |
print(ea)
|
37 |
try:
|
38 |
if not ea['URL'].startswith("http"):
|
@@ -44,7 +44,7 @@ def sitemap(url,level):
|
|
44 |
out_list=link_find(f"{uri}{ea['URL']}")
|
45 |
#link1[i]['TREE']=out_list
|
46 |
if level>=3:
|
47 |
-
for n,na in enumerate(link1[i]['TREE']):
|
48 |
print(na)
|
49 |
try:
|
50 |
if not na['URL'].startswith("http"):
|
@@ -60,6 +60,42 @@ def sitemap(url,level):
|
|
60 |
except Exception as e:
|
61 |
print (e)
|
62 |
return link1
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
63 |
with gr.Blocks() as app:
|
64 |
with gr.Row():
|
65 |
inp=gr.Textbox(label="URL")
|
|
|
24 |
|
25 |
else:
|
26 |
pass
|
27 |
+
return node1
|
28 |
#https://huggingface.co/spaces/Omnibus/crawl
|
29 |
|
30 |
def sitemap(url,level):
|
|
|
32 |
if url != "" and url != None:
|
33 |
link1=link_find(url)
|
34 |
if level >=2:
|
35 |
+
for i,ea in enumerate(link1['TREE']):
|
36 |
print(ea)
|
37 |
try:
|
38 |
if not ea['URL'].startswith("http"):
|
|
|
44 |
out_list=link_find(f"{uri}{ea['URL']}")
|
45 |
#link1[i]['TREE']=out_list
|
46 |
if level>=3:
|
47 |
+
for n,na in enumerate(link1['TREE'][i]['TREE']):
|
48 |
print(na)
|
49 |
try:
|
50 |
if not na['URL'].startswith("http"):
|
|
|
60 |
except Exception as e:
|
61 |
print (e)
|
62 |
return link1
|
63 |
+
|
64 |
+
|
65 |
+
|
66 |
+
def sitemap_OG(url,level):
|
67 |
+
uri=""
|
68 |
+
if url != "" and url != None:
|
69 |
+
link1=link_find(url)
|
70 |
+
if level >=2:
|
71 |
+
for i,ea in enumerate(link1):
|
72 |
+
print(ea)
|
73 |
+
try:
|
74 |
+
if not ea['URL'].startswith("http"):
|
75 |
+
uri1=url.split("//")[0]
|
76 |
+
uri2=url.split("//")[1]
|
77 |
+
uri3=uri2.split("/")[0]
|
78 |
+
uri=f'{uri1}//{uri3}'
|
79 |
+
print(uri)
|
80 |
+
out_list=link_find(f"{uri}{ea['URL']}")
|
81 |
+
link1[i]['TREE']=out_list
|
82 |
+
if level>=3:
|
83 |
+
for n,na in enumerate(link1[i]['TREE']):
|
84 |
+
print(na)
|
85 |
+
try:
|
86 |
+
if not na['URL'].startswith("http"):
|
87 |
+
uri11=url.split("//")[0]
|
88 |
+
uri22=url.split("//")[1]
|
89 |
+
uri33=uri22.split("/")[0]
|
90 |
+
uri0=f'{uri11}//{uri33}'
|
91 |
+
print(uri0)
|
92 |
+
out_list1=link_find(f"{uri0}{na['URL']}")
|
93 |
+
link1[i]['TREE'][n]['TREE']=out_list1
|
94 |
+
except Exception as e:
|
95 |
+
print (e)
|
96 |
+
except Exception as e:
|
97 |
+
print (e)
|
98 |
+
return link1
|
99 |
with gr.Blocks() as app:
|
100 |
with gr.Row():
|
101 |
inp=gr.Textbox(label="URL")
|